dist_of_trip_duration_age_grp_gender

manhattan_rides_df <- read_csv("manhattan_rides.csv")

trip_dur_age_gender_df <-
  manhattan_rides_df %>% 
  select(trip_min, gender, age_group) %>% 
  mutate(
    age_group = factor(age_group, ordered = T,
                       levels = c("18-25","26-35", "36-45", "46-55", "56-65", "66-85")),
    gender = type.convert(gender, as.is = F)
  )

Q1 <- quantile(pull(trip_dur_age_gender_df, trip_min), probs = 0.25)
Q3 <- quantile(pull(trip_dur_age_gender_df, trip_min), probs = 0.75)
inter_quart <- IQR(pull(trip_dur_age_gender_df, trip_min))

trip_dur_age_gender_df <-
  trip_dur_age_gender_df %>% 
    filter(
      trip_min >= Q1 - 1.5*inter_quart, 
      trip_min <= Q3 + 1.5*inter_quart
    )

trip_dur_age_gender_df %>% 
  mutate(
    gender = str_to_sentence(gender)
  ) %>% 
  plot_ly(x = ~age_group, y = ~trip_min, color = ~gender, type = "box", colors = "viridis") %>%  
  layout(
    boxmode = "group",
    xaxis = list(title = "Age Range"), 
    yaxis = list(title = "Trip Duration (min)"), 
    legend = list(title = list(text = '<b> Gender </b>'))
  )